-
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
Paper • 2502.14669 • Published • 14 -
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Paper • 2503.05592 • Published • 27 -
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24
Abhranil Chandra PRO
abhranil14
AI & ML interests
Reinforcement Learning, Deep Unsupervised Learning, NLP and Bayesian Deep Learning
Recent Activity
updated
a dataset
about 1 month ago
MilaAI4Math/Final_Datasets_Preprocessed_for_Reasoning_from_Wrong_CoTs
updated
a dataset
about 1 month ago
MilaAI4Math/Final_GSM8k_Dataset
published
a dataset
about 1 month ago
MilaAI4Math/Final_GSM8k_Dataset
Organizations
-
AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO
Paper • 2502.14669 • Published • 14 -
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Paper • 2503.05592 • Published • 27 -
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24
models
51
abhranil14/gemma2_2B_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_2048
Updated
abhranil14/llama_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_1024
Updated
abhranil14/llama_FF_self_distill_gold_batch256_lr10e-6_warmup0.1_correct_1perqs_new
Updated
abhranil14/Gemma2B_FF_on_qwen14B_wrong_2130_batch256_lr10e-6_warmup0.1_30_epoch_linear_lr
Updated
abhranil14/Qwen1.5B_FF_on_human_gold_7500_batch256_lr10e-6_warmup0.1_linear_lr
Updated
abhranil14/Gemma2B_FF_on_human_gold_7500_batch256_lr10e-6_warmup0.1
Updated
abhranil14/Gemma_FF_on_Gemma27B_wrong_soln_wrt_human_1_soln_per_qs_6076_batch256_lr10e-6_warmup0.1
Updated
abhranil14/Gemma2B_FF_on_qwen14B_gold_6158_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr
Updated
abhranil14/Gemma2B_FF_on_gemma2B_self_distill_wrong_7044_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr
Updated
abhranil14/Gemma2B_FF_on_gemma2B_self_distill_gold_1295_batch256_lr10e-6_warmup0.1_54_epoch_linear_lr
Updated
datasets
5
abhranil14/VideoAgent_Data
Preview
•
Updated
•
7
abhranil14/syn_qs_and_soln_cleaned_0_and_less20_multiple_soln_per_qs_1937545
Viewer
•
Updated
•
1.94M
•
16
abhranil14/syn_qs_and_soln_cleaned_0_and_less20_1_soln_per_qs_131845
Viewer
•
Updated
•
132k
•
8
abhranil14/instruct-human-assistant-prompt-clean-105k
Viewer
•
Updated
•
105k
•
4
abhranil14/first-instruct-human-assistant-prompt-clean-33k
Viewer
•
Updated
•
33.1k
•
9